Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 11149
    Prev
    Next
    INDEX
    Explanations

    font names and related terms

    oai_token-act-pair · gemini-2.0-flash

    font types and styles

    np_token-act-pair-logits · gpt-4o-mini

    font faces

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_21/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EndInit
    -0.79
     ModelExpression
    -0.72
     noqa
    -0.64
    StoryboardSegue
    -0.62
    NSIndexPath
    -0.61
    PageRoute
    -0.57
    IntoConstraints
    -0.56
     initComponents
    -0.56
    ,:);
    -0.54
    bufio
    -0.53
    POSITIVE LOGITS
     face
    0.79
    face
    0.77
    Face
    0.71
     sans
    0.66
    faces
    0.65
     regular
    0.63
     type
    0.60
     Face
    0.60
    faced
    0.58
     ker
    0.57
    Activations Density 2.110%

    No Known Activations